@brainervirus/workit-codex 8.18.0 → 8.19.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (10) hide show
  1. package/.codex-plugin/plugin.json +1 -1
  2. package/agents/workit-reviewer.toml +3 -2
  3. package/agents/workit-verifier.toml +4 -3
  4. package/dist/launch-mcp.js +4405 -4405
  5. package/dist/{workit-hook-q9ypsecg.js → workit-hook-rkwtxnyc.js} +3840 -3811
  6. package/dist/workit-hook.js +1 -1
  7. package/package.json +3 -3
  8. package/skills/workit-implement/SKILL.md +5 -3
  9. package/skills/workit-verify-app/SKILL.md +6 -2
  10. package/skills/workit-verify-app/references/template.md +2 -0
package/.codex-plugin/plugin.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "workit",
3
- "version": "8.18.0",
3
+ "version": "8.19.1",
4
4
  "description": "Adaptive engineering workflow rails for Codex",
5
5
  "author": {
6
6
  "name": "BrainerVirus"
package/agents/workit-reviewer.toml CHANGED
@@ -17,8 +17,9 @@ description of it. Follow the workit-review skill (`$workit-review`).
17
17
  4. Each finding: file:line, severity (blocker, major, minor, nit), evidence
18
18
  (hunk, test or command output), concrete fix.
19
19
  5. Record the verdict:
20
- `workit ledger verdict verified|failed|blocked --kind review --branch <b> --session <id> --token <token> --how "<what you read and ran>"`,
21
- with the session and token the SubagentStart hook gave you (the token is yours alone: never put it in a report)
20
+ start from the exact verdict command the SubagentStart hook put in your context (it
21
+ carries your session and `--token=<token>`; the token is yours alone: never put it in a report); it already names `--kind review`:
22
+ `workit ledger verdict verified|failed|blocked --kind review --branch <b> --session <id> --token=<token> --how "<what you read and ran>"`
22
23
  (`verified` with `--kind review`: no blocker or major finding left).
23
24
  Record a design choice you had to make as `workit ledger ruling`.
24
25
 
package/agents/workit-verifier.toml CHANGED
@@ -20,9 +20,10 @@ it.
20
20
  5. Judge each acceptance line as met, not met, or not verifiable, citing what
21
21
  you observed. Label every claim measured, inferred or guess.
22
22
  6. Record the verdict, then report it:
23
- `workit ledger verdict verified|tests-verified|type-check-only|failed|blocked --branch <b> --kind live|unit --session <id> --token <token> --how "<what you ran and saw>"`,
24
- with the session and token the SubagentStart hook gave you (you share the lead's
25
- `WORKIT_SESSION_ID`, which authored the work).
23
+ start from the exact verdict command the SubagentStart hook put in your context (it
24
+ carries your session and `--token=<token>`; you share the lead's
25
+ `WORKIT_SESSION_ID`, which authored the work) and pick its `--kind <live|unit>`:
26
+ `workit ledger verdict verified|tests-verified|type-check-only|failed|blocked --kind <live|unit> --branch <b> --session <id> --token=<token> --how "<what you ran and saw>"`.
26
27
  `verified` means the change was observed working on its real surface
27
28
  (verify-<app>, `--kind live`); `tests-verified` means only tests ran. If the ledger refuses you as an author, report that;
28
29
  never pass `--self` to get around it.